README.md

metadata

language: zh
tags:
  - simcse
datasets:
  - dialogue

Data

train data is similarity sentence data from E-commerce dialogue

Model

model created by sentence-tansformers，model struct is cross-encoder

Usage

>>> from transformers import AutoTokenizer, AutoModel
>>> model = AutoModel.from_pretrained("tuhailong/simcse_model")
>>> tokenizer = AutoTokenizer.from_pretrained("tuhailong/simcse_model")
>>> sentences_str_list = ["今天天气不错的","天气不错的"]
>>> inputs = tokenizer(sentences_str_list,return_tensors="pt", padding='max_length', truncation=True, max_length=32)
>>> outputs = model(**inputs)